CLAUDE.md template for a Next.js + Supabase appTemplateLow risk
A ready-to-edit CLAUDE.md that tells Claude Code how your Next.js app is built, tested and deployed.
Templates and prompts for the files coding agents read before they touch your code: CLAUDE.md for Claude Code, AGENTS.md for Codex, Jules and Cursor, Cursor project rules, GitHub Copilot instructions, plus Claude Code slash commands and subagents. Fill in the blanks, drop the file in your repo, and your agent stops guessing how your project works.
A ready-to-edit CLAUDE.md that tells Claude Code how your Next.js app is built, tested and deployed.
Project memory for Claude Code on a Python API: commands, layout, testing and the rules that keep it safe.
One root AGENTS.md plus per-package overrides so Codex, Cursor, Jules and other agents work the same way everywhere.
Have your coding agent read the repo and write an accurate AGENTS.md instead of guessing.
End-of-session prompt that turns what the agent learned into permanent project memory.
A .cursor/rules/*.mdc file that keeps Cursor's agent consistent with your React codebase.
A .github/copilot-instructions.md that makes Copilot chat and agent mode follow your repo's rules.
Save as .claude/commands/review.md to get a one-word, consistent code review in Claude Code.
A .claude/agents/test-writer.md subagent that writes focused tests in your project's style.
Write your project rules once and get the file every major coding agent reads.
Paste into CLAUDE.md or AGENTS.md so agents stop declaring victory before the work is verified.
A 'never do' section for CLAUDE.md / AGENTS.md that prevents the expensive mistakes.
A reusable AGENTS.md that stops your AI agent from guessing.
Package a repeatable task into instructions an agent can load on demand.